Uncertainty-Based Active Learning via Sparse Modeling for Image Classification.

Uncertainty sampling-based active learning has been well studied for selecting informative samples to improve the performance of a classifier. In batch-mode active learning, a batch of samples are selected for a query at the same time. The samples with top uncertainty are encouraged to be selected. However, this selection strategy ignores the relations among the samples, because the selected samples may have much redundant information with each other. This paper addresses this problem by proposing a novel method that combines uncertainty, diversity, and density via sparse modeling in the sample selection. We use sparse linear combination to represent the uncertainty of unlabeled pool data with Gaussian kernels, in which the diversity and density are well incorporated. The selective sampling method is proposed before optimization to reduce the representation error. To deal with ${l}_{0}$ norm constraint in the sparse problem, two approximated approaches are adopted for efficient optimization. Four image classification data sets are used for evaluation. Extensive experiments related to batch size, feature space, seed size, significant analysis, data transform, and time efficiency demonstrate the advantages of the proposed method.

Effects of ocean warming and acidification, combined with nutrient enrichment, on chemical composition and functional properties of Ulva rigida.

Ulva is increasingly viewed as a food source in the world. Here, Ulva rigida was cultured at two levels of temperature (14, 18 °C), pH (7.95, 7.55, corresponding to low and high pCO2), and nitrate conditions (6 µmol L-1, 150 µmol L-1), to investigate the effects of ocean warming, acidification, and eutrophication on food quality of Ulva species. High temperature increased the content of each amino acid. High nitrate increased the content of all amino acids except aspartic acid and cysteine. High temperature, pCO2, and nitrate also increased the content of most fatty acids. The combination of high temperature, pCO2, and nitrate increased the swelling capacity, water holding capacity, and oil holding capacity by 15.60%, 7.88%, and 16.32% respectively, compared to the control. It seems that the future ocean environment would enhance the production of amino acid and fatty acid as well as the functional properties of Ulva species.

Eutrophication and warming-driven green tides (Ulva rigida) are predicted to increase under future climate change scenarios.

The incidence and severity of extraordinary macroalgae blooms (green tides) are increasing. Here, climate change (ocean warming and acidification) impacts on life history and biochemical responses of a causative green tide species, Ulva rigida, were investigated under combinations of pH (7.95, 7.55, corresponding to lower and higher pCO2), temperature (14, 18°C) and nitrate availability (6 and 150µmolL-1). The higher temperature accelerated the onset and magnitude of gamete settlement. Any two factor combination promoted germination and accelerated growth in young plants. The higher temperature increased reproduction, which increased further in combination with elevated pCO2 or nitrate. Reproductive success was highest (64.4±5.1%) when the upper limits of all three variables were combined. Biochemically, more protein and lipid but less carbohydrate were synthesized under higher temperature and nitrate conditions. These results suggest that climate change may cause more severe green tides, particularly when eutrophication cannot be effectively controlled.